forked from OSchip/llvm-project
117 lines
3.8 KiB
LLVM
117 lines
3.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=X32
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=X32
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=X64
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=X64
|
|
|
|
define <2 x double> @fabs_v2f64(<2 x double> %p) {
|
|
; X32-LABEL: fabs_v2f64:
|
|
; X32: # BB#0:
|
|
; X32-NEXT: vandpd .LCPI0_0, %xmm0, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: fabs_v2f64:
|
|
; X64: # BB#0:
|
|
; X64-NEXT: vandpd {{.*}}(%rip), %xmm0, %xmm0
|
|
; X64-NEXT: retq
|
|
%t = call <2 x double> @llvm.fabs.v2f64(<2 x double> %p)
|
|
ret <2 x double> %t
|
|
}
|
|
declare <2 x double> @llvm.fabs.v2f64(<2 x double> %p)
|
|
|
|
define <4 x float> @fabs_v4f32(<4 x float> %p) {
|
|
; X32-LABEL: fabs_v4f32:
|
|
; X32: # BB#0:
|
|
; X32-NEXT: vandps .LCPI1_0, %xmm0, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: fabs_v4f32:
|
|
; X64: # BB#0:
|
|
; X64-NEXT: vandps {{.*}}(%rip), %xmm0, %xmm0
|
|
; X64-NEXT: retq
|
|
%t = call <4 x float> @llvm.fabs.v4f32(<4 x float> %p)
|
|
ret <4 x float> %t
|
|
}
|
|
declare <4 x float> @llvm.fabs.v4f32(<4 x float> %p)
|
|
|
|
define <4 x double> @fabs_v4f64(<4 x double> %p) {
|
|
; X32-LABEL: fabs_v4f64:
|
|
; X32: # BB#0:
|
|
; X32-NEXT: vandpd .LCPI2_0, %ymm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: fabs_v4f64:
|
|
; X64: # BB#0:
|
|
; X64-NEXT: vandpd {{.*}}(%rip), %ymm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%t = call <4 x double> @llvm.fabs.v4f64(<4 x double> %p)
|
|
ret <4 x double> %t
|
|
}
|
|
declare <4 x double> @llvm.fabs.v4f64(<4 x double> %p)
|
|
|
|
define <8 x float> @fabs_v8f32(<8 x float> %p) {
|
|
; X32-LABEL: fabs_v8f32:
|
|
; X32: # BB#0:
|
|
; X32-NEXT: vandps .LCPI3_0, %ymm0, %ymm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: fabs_v8f32:
|
|
; X64: # BB#0:
|
|
; X64-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%t = call <8 x float> @llvm.fabs.v8f32(<8 x float> %p)
|
|
ret <8 x float> %t
|
|
}
|
|
declare <8 x float> @llvm.fabs.v8f32(<8 x float> %p)
|
|
|
|
; PR20354: when generating code for a vector fabs op,
|
|
; make sure that we're only turning off the sign bit of each float value.
|
|
; No constant pool loads or vector ops are needed for the fabs of a
|
|
; bitcasted integer constant; we should just return an integer constant
|
|
; that has the sign bits turned off.
|
|
;
|
|
; So instead of something like this:
|
|
; movabsq (constant pool load of mask for sign bits)
|
|
; vmovq (move from integer register to vector/fp register)
|
|
; vandps (mask off sign bits)
|
|
; vmovq (move vector/fp register back to integer return register)
|
|
;
|
|
; We should generate:
|
|
; mov (put constant value in return register)
|
|
|
|
define i64 @fabs_v2f32_1() {
|
|
; X32-LABEL: fabs_v2f32_1:
|
|
; X32: # BB#0:
|
|
; X32-NEXT: xorl %eax, %eax
|
|
; X32-NEXT: movl $2147483647, %edx # imm = 0x7FFFFFFF
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: fabs_v2f32_1:
|
|
; X64: # BB#0:
|
|
; X64-NEXT: movabsq $9223372032559808512, %rax # imm = 0x7FFFFFFF00000000
|
|
; X64-NEXT: retq
|
|
%bitcast = bitcast i64 18446744069414584320 to <2 x float> ; 0xFFFF_FFFF_0000_0000
|
|
%fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %bitcast)
|
|
%ret = bitcast <2 x float> %fabs to i64
|
|
ret i64 %ret
|
|
}
|
|
|
|
define i64 @fabs_v2f32_2() {
|
|
; X32-LABEL: fabs_v2f32_2:
|
|
; X32: # BB#0:
|
|
; X32-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF
|
|
; X32-NEXT: xorl %edx, %edx
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: fabs_v2f32_2:
|
|
; X64: # BB#0:
|
|
; X64-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF
|
|
; X64-NEXT: retq
|
|
%bitcast = bitcast i64 4294967295 to <2 x float> ; 0x0000_0000_FFFF_FFFF
|
|
%fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %bitcast)
|
|
%ret = bitcast <2 x float> %fabs to i64
|
|
ret i64 %ret
|
|
}
|
|
|
|
declare <2 x float> @llvm.fabs.v2f32(<2 x float> %p)
|